Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4646 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.3241. Min Act: -0.0000

Data Index: 1061078 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.1362. Min Act: -0.0000

Data Index: 1214679 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 1.3241. Min Range: -1.3241

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1263815 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.9950. Min Act: -0.0000

Data Index: 461606 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.9092. Min Act: -0.0000

Data Index: 24663 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.9827. Min Act: -0.0000

Data Index: 78782 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.9405. Min Act: -0.0000

Data Index: 454886 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.8802. Min Act: -0.0000

Data Index: 166635 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.8743. Min Act: -0.0000

Data Index: 721670 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.8171. Min Act: -0.0000

Data Index: 235762 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.7928. Min Act: -0.0000

Data Index: 970159 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.8194. Min Act: -0.0000

Data Index: 966970 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.8032. Min Act: -0.0000

Data Index: 514735 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.8197. Min Act: -0.0000

Data Index: 581715 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.7935. Min Act: -0.0000

Data Index: 800585 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.8082. Min Act: -0.0000

Data Index: 571379 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.7599. Min Act: -0.0000

Data Index: 647197 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.7702. Min Act: -0.0000

Data Index: 349787 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.8164. Min Act: -0.0000

Data Index: 623280 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.3241. Min Range: -1.3241

Max Act: 0.7747. Min Act: -0.0000

Data Index: 378313 (C4 (Web Text))

Max Activating Token Index: 58